Pipe Routing using Reinforcement Learning on Initial Design Stage

2020 ◽  
Vol 57 (4) ◽  
pp. 191-197
Author(s):  
Dong-seon Shin ◽  
Byeong-cheol Park ◽  
Chae-og Lim ◽  
Sang-jin Oh ◽  
Gi-yong Kim ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Design Stage ◽  
Initial Design ◽  
Pipe Routing

scholarly journals Development of Design Process Simulator for the Ship Initial Design Stage

2009 ◽  
Vol 9 (0) ◽  
pp. 211-222
Author(s):  
Kunihiro Hamada ◽  
Mitsuru Kitamura ◽  
Souichi Yasui ◽  
Hiroshi Kawasaki
Keyword(s):  
Design Process ◽  
Design Stage ◽  
Initial Design ◽  
Process Simulator

scholarly journals The influence of exterior obstruction on the integrated evaluation of daylight utilization during initial design stage

2017 ◽  
Vol 205 ◽  
pp. 2785-2792
Author(s):  
Jingting Sun ◽  
Zhengrong Li ◽  
Fu Xiao
Keyword(s):  
Design Stage ◽  
Initial Design

Development of a Methodology for Determining the Best Option for the Route of the Heat Network at the Initial Design Stage

2021 ◽  
pp. 57-64
Author(s):  
А. А. Чуйкина
Keyword(s):  
Mathematical Model ◽  
Vector Optimization ◽  
Optimization Problem ◽  
Pairwise Comparison ◽  
Design Stage ◽  
Heat Network ◽  
Thermal Network ◽  
Initial Design ◽  
Matrix Generalization ◽  
Joint Application

Постановка задачи. Выбор наилучшего варианта трассы тепловой сети на начальном этапе проектирования является сложной многофакторной задачей, кроме того, ввиду отсутствия ряда необходимых конструктивных расчетов ее решение сопровождается ограниченностью набора исходных данных. Таким образом, становится актуальной разработка новой методики проектирования оптимальной трассы системы теплоснабжения, учитывающей качественные и количественные характеристики рассматриваемого объекта. Результаты. Разработана математическая модель обобщенного аддитивного векторного критерия оптимальности, учитывающая материалоемкость тепловой сети, ее надежность, время строительства, годовые тепловые потери, оборот теплоты и дисперсию температуры у потребителя. Предложен способ определения наилучшего варианта трассы тепловой сети на начальном этапе проектирования путем совместного решения задачи оптимизации методами векторной оптимизации и матричного обобщения. Отмечена целесообразность совместного применения методов попарного сравнения и векторной оптимизации при решении рассматриваемой задачи. Выводы. Важной характеристикой разработанной математической модели обобщенного критерия является возможность получения более точного решения рассматриваемой оптимизационной задачи при неравномерным распределении тепловой нагрузки посредством смещенной оценки дисперсии температуры у потребителей. Совместное применение методов матричного обобщения, попарного сравнения и векторной оптимизации позволяет повысить точность расчета при решении оптимизационной задачи выбора наилучшей трассы тепловой сети. Statement of the problem. Choosing the best option for the route of the thermal network at the initial stage of design is a complex multifactorial task, in addition, due to the lack of a number of necessary design calculations, its solution is accompanied by a limited set of initial data. Thus, it becomes relevant to develop a new methodology for designing the optimal route of the heat supply system, taking into account the qualitative and quantitative characteristics of the object under consideration. Results. A mathematical model of a generalized additive vector optimality criterion has been developed, taking into account the material consumption of the heat network, its reliability, construction time, annual thermal losses, heat turnover and temperature dispersion at the consumer. A method is proposed for determining the best option for the route of a thermal network at the initial design stage by jointly solving the optimization problem using vector optimization and matrix generalization methods. The expediency of the joint application of the methods of pairwise comparison and vector optimization in solving the problem under consideration is noted. Conclusions. An important characteristic of the developed mathematical model of the generalized criterion is the possibility of obtaining a more accurate solution to the optimization problem under consideration with an uneven distribution of the heat load by means of a biased estimate of the temperature variance among consumers. The combined application of the methods of matrix generalization, pairwise comparison and vector optimization can improve the accuracy of the calculation when solving the optimization problem of choosing the best route of the thermal network.

Hybrid system approach to optimum design of a ship

1999 ◽  
Vol 13 (1) ◽  
pp. 1-11 ◽  
Author(s):  
DONGKON LEE
Keyword(s):  
Optimum Design ◽  
Hybrid System ◽  
Optimization Algorithm ◽  
Search Method ◽  
Design Stage ◽  
Search Efficiency ◽  
Knowledge Based System ◽  
Initial Design ◽  
Optimum Point ◽  
Knowledge Based

To obtain optimal design efficiently in the initial design stage of a ship, a hybrid system is developed by integrating the optimization algorithm and knowledge-based system. The hybrid system can manipulate numeric and symbolic data simultaneously. To increase search efficiency in a design space, the optimization algorithm (optimizer) is implemented by coupling a genetic algorithm (GA) and search method. The optimizer determines a candidate region around the optimum point by using the GA, then searches the optimum point by the search method concentrating in this region, thus reducing calculation time and increasing search efficiency. To generate input data for the optimizer, a rule-based system is developed. Some domain knowledge for ship optimization in the initial design stage is retrieved from a database of existing ship and design experts. The obtained knowledge is stored in the knowledge base. The optimizer incorporates a knowledge-based system with heuristic and analytic knowledge, thereby narrowing the feasible space of the design variables. Therefore, search speed and the capability of finding an optimum point will be increased in comparison with conventional approach. The developed system is applied principally to particulars of optimization of ships with multicriteria. Through application ship design, it shows that the hybrid system can be a useful tool for optimum design.

scholarly journals Application of Machine Learning Algorithms for Solving Problems in the Oil and Gas Sector

2021 ◽  
Vol 19 (3) ◽  
pp. 55-64
Author(s):  
K. N. Maiorov ◽  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Reinforcement Learning ◽  
Machine Learning Algorithms ◽  
Design Stage ◽  
Learning Methods ◽  
Field Development ◽  
Advantages And Disadvantages ◽  
Machine Learning Methods ◽  
The Neural Network

The paper examines the life cycle of field development, analyzes the processes of the field development design stage for the application of machine learning methods. For each process, relevant problems are highlighted, existing solutions based on machine learning methods, ideas and problems are proposed that could be effectively solved by machine learning methods. For the main part of the processes, examples of solutions are briefly described; the advantages and disadvantages of the approaches are identified. The most common solution method is feed-forward neural networks. Subject to preliminary normalization of the input data, this is the most versatile algorithm for regression and classification problems. However, in the problem of selecting wells for hydraulic fracturing, a whole ensemble of machine learning models was used, where, in addition to a neural network, there was a random forest, gradient boosting and linear regression. For the problem of optimizing the placement of a grid of oil wells, the disadvantages of existing solutions based on a neural network and a simple reinforcement learning approach based on Markov decision-making process are identified. A deep reinforcement learning algorithm called Alpha Zero is proposed, which has previously shown significant results in the role of artificial intelligence for games. This algorithm is a decision tree search that directs the neural network: only those branches that have received the best estimates from the neural network are considered more thoroughly. The paper highlights the similarities between the tasks for which Alpha Zero was previously used, and the task of optimizing the placement of a grid of oil producing wells. Conclusions are made about the possibility of using and modifying the algorithm of the optimization problem being solved. Аn approach is proposed to take into account symmetric states in a Monte Carlo tree to reduce the number of required simulations.

Product Design Analysis Using the Assembly Design Evaluation Metric

1991 ◽  
Author(s):  
David E. Lee ◽  
Michel A. Melkanoff
Keyword(s):  
Product Design ◽  
Design Analysis ◽  
Design Stage ◽  
Design Evaluation ◽  
Generic Model ◽  
Design Data ◽  
Assembly Design ◽  
Initial Design ◽  
Evaluation Metric ◽  
Assembly Operations

Abstract Analysis of a product’s assembly properties is needed during the initial design stage in order to identify potential assembly problems. These problems affect product performance in the later stages of a product’s life cycle. An analysis methodology has been developed that supports product design analysis for assembly during the initial design stage. The methodology, referred to as the Assembly Design Evaluation Metric (ADEM), utilizes the incomplete nature of initial design data and a generic model of assembly operations in the analysis of a product design. ADEM generates ratings for each component of a product design and each process that would be needed to assemble the components together. From the individual component and process ratings, ADEM computes overall ratings for the product design itself. These overall product ratings can then be used to compare the differing iterations of a product design. Because ADEM provides an explicit model of assembly operations, different levels of data and process abstraction can be maintained and analyzed. This enables ADEM to evaluate product designs earlier in the design stage than existing design analysis methods such as DFA (design for assembly) techniques.

Sign in / Sign up

Export Citation Format

Share Document